Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2768 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1723. Min Range: -5.1723
Max Act: 5.1723. Min Act: -0.1700
Data Index: 4802745 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1723. Min Range: -5.1723
Max Act: 5.0161. Min Act: -0.1700
Data Index: 3449059 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1723. Min Range: -5.1723
Max Act: 4.8911. Min Act: -0.1700
Data Index: 2830095 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1723. Min Range: -5.1723
Max Act: 4.8286. Min Act: -0.1700
Data Index: 906329 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1723. Min Range: -5.1723
Max Act: 4.7036. Min Act: -0.1700
Data Index: 6249319 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1723. Min Range: -5.1723
Max Act: 4.7661. Min Act: -0.1700
Data Index: 7407633 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1723. Min Range: -5.1723
Max Act: 4.7348. Min Act: -0.1700
Data Index: 3605608 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1723. Min Range: -5.1723
Max Act: 4.7036. Min Act: -0.1700
Data Index: 7954694 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1723. Min Range: -5.1723
Max Act: 4.7348. Min Act: -0.1700
Data Index: 5624046 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1723. Min Range: -5.1723
Max Act: 4.6411. Min Act: -0.1700
Data Index: 4629413 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1723. Min Range: -5.1723
Max Act: 4.6723. Min Act: -0.1700
Data Index: 4853440 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1723. Min Range: -5.1723
Max Act: 4.6411. Min Act: -0.1700
Data Index: 312436 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1723. Min Range: -5.1723
Max Act: 4.6098. Min Act: -0.1700
Data Index: 7214406 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1723. Min Range: -5.1723
Max Act: 4.5786. Min Act: -0.1700
Data Index: 1322169 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1723. Min Range: -5.1723
Max Act: 4.5473. Min Act: -0.1700
Data Index: 1989389 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1723. Min Range: -5.1723
Max Act: 4.5786. Min Act: -0.1700
Data Index: 8516999 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1723. Min Range: -5.1723
Max Act: 4.5473. Min Act: -0.1700
Data Index: 4397175 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1723. Min Range: -5.1723
Max Act: 4.5473. Min Act: -0.1700
Data Index: 8551473 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1723. Min Range: -5.1723
Max Act: 4.5161. Min Act: -0.1700
Data Index: 1437550 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1723. Min Range: -5.1723
Max Act: 4.5161. Min Act: -0.1700
Data Index: 1350432 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19